"Code Execution" matching MCP servers:

Enables execution of SAS code on SAS Viya compute environments with OAuth2 authentication. Allows users to run SAS programs and retrieve execution results including logs and output through the Model Context Protocol.

Enables MCP-capable LLMs to generate and render ephemeral Prefab UI interfaces at runtime, with tools for generating UI code and searching Prefab components.

Enables MCP clients to screen lab results against published criteria with deterministic Python, search Australian contaminated-land guidance with cited passages, and draft guarded results sections whose numbers and citations are validated. All four tools are read-only and keep figures and citations under code control for a qualified person to check.

Enables AI assistants to interact with DBT (Data Build Tool) projects, allowing them to query project metadata, inspect models and sources, view compiled SQL, and run DBT commands.

MCP server for AI Diagram Maker — generate software engineering diagrams from natural language, code, ASCII diagram, images, or Mermaid. Inline diagram rendering using MCP apps UI and diagram URL in responses. Works with Cursor, Claude Desktop, Claude Code, and any MCP-compatible AI.

Hermetic memory for AI agents — one Rust binary, one SQLite file, zero network. Recall returns evidence with provenance or abstains: no code path for making things up.

Read-only MCP server for searching Yahoo! Shopping products through the Yahoo! Shopping Item Search API v3. It supports keyword and JAN-code search with price, stock, condition, shipping, sorting, category, brand, seller, image-size, and pagination filters.

Read-only VMware vCenter/ESXi monitoring. 8 MCP tools for VM inventory, host status, datastore capacity, cluster info, alarms, events, and VM details. Code-level enforced safety — no destructive operations exist in the codebase. Supports vSphere 6.5–8.0. Works with local models via Ollama/LM Studio.

Lets AI agents draw professional cloud architecture diagrams with the official AWS, Azure and Google Cloud icons, from a plain description, a JSON graph or Terraform code.

Enables AI coding agents to vet an npm release against the package's own history — publisher, provenance, install scripts, new dependencies, code changes — before installing or upgrading it. Returns an ALLOW / REVIEW / BLOCK verdict with supporting evidence, what other checks say, and the safe version to install instead.

Multi-provider image generation MCP server that enables image generation from Claude Desktop, Claude Code, or any MCP client using OpenAI, Google Gemini, Stable Diffusion, or a placeholder provider.

An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.

Enables AI agents to render interactive Highcharts visualizations directly within VS Code chat conversations. It supports over 17 chart types with GitHub Primer styling and advanced features like drilldown and WebGL rendering.

RunBeacon is an MCP server that turns long-running local and SSH commands into tracked jobs. It provides event-driven monitoring, a live dashboard, and a resident daemon for reliable execution and cancellation.

Bridges Gitee, China's largest code hosting platform, to MCP for exploring trending repos, searching users/repos, and translating Chinese content with a local LLM.

A read-only task graph visualizer for Beads projects, running as an MCP server in Claude Desktop or VS Code Copilot to display interactive DAGs, list views, and stats dashboards.

MCP server for the Codex Bilingual Overlay, enabling control of bilingual translation modes (off, hover, preload) and retrieval of overlay status for the Codex desktop app.

Enables coding agents to retrieve only the JavaScript/TypeScript code needed for a given task within a token budget, using TypeScript compiler analysis and a decision model to judge relevance.

Local MCP server for YueShu Graph 5.3 enabling safe GQL validation and execution, schema discovery, and structured graph/chart results through Codex.

Enables AI agents to issue, correct, and register legally compliant Spanish electronic invoices with AEAT VeriFactu, supporting F1/F2 types, R1–R5 correctives, and NIF validation from Claude, ChatGPT, Cursor, or VS Code.

MCP server for Threadlinqs Intelligence — 49 tools across threat intelligence, detections, IOCs, threat actors, MITRE attack-chains, C2 infrastructure, and Purple-tier composite intelligence. Drop-in for Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.

Enables MCP clients such as Claude Code, Codex, and Cursor to run Textile Designer AI's textile design tools on image files and URLs — upscaling, repeats, background and watermark removal, channeling, colourways, vectorizing, and more — and save the results locally. Handles device-code account login, plan and credit checks, cost estimates, and job status/download for long-running runs.

Enables AI assistants to create, edit, and simulate EnergyPlus building energy models via natural language. Supports schema exploration, model editing, simulation execution, and documentation search.

Allows Claude desktop app to execute terminal commands and edit files on your computer through MCP, with features including command execution, process management, and diff-based file editing.

让两个 AI 在同一个对话里替你互相把关

Enables users to explore a local repository’s commit history through read-only MCP tools, including branch lanes, merge edges, branch selection, search highlighting, commit metadata, file statistics, and bounded patches.

Local server that lets Claude Code and Claude Desktop drive NotebookLM and Google Flow through the user's own logged-in Edge or Chrome session instead of a paid API, covering notebooks, sources, cited answers, Studio outputs (audio/video overviews, slides, reports, mind maps, quizzes) and image/video generation with Veo. It also self-verifies the buttons, menus and internal calls it relies on and reports exactly what the provider changed.

Enables comprehensive Windows system management through Claude Desktop, including PowerShell/CMD execution, file operations, archive handling, Git tools, network testing, and system monitoring. Provides a complete toolkit for Windows automation and administration tasks.

Enables persistent SQLite-backed tasks, recorded parent/child agent relationships, workflow groups, and lead-mediated conversation snapshots and navigation requests through compatible ChatGPT/Codex hosts.

An MCP server for Claude Desktop, Cowork and Claude Code that plans a task in parts and hands the simple ones, like reading files, searching and drafting, to cheaper or free models, so the Claude plan lasts longer. Each answer comes back with a receipt for Claude to review and grade.